Explore the corpus

Find evidence, not just documents.

Search Minerva’s current Findings using transparent hybrid retrieval. Results remain strictly inside the configured corpus.

Hybrid retrieval

Results for “Natural Language Processing in Financial Markets”

30 findings

68match

Finding 37721 source

Researchers combine speech emotion recognition and natural language processing with high-frequency financial data to demonstrate how ECB press conferences' vocal, verbal cues impact euro area bond yields and equity prices.

LexicalMeaningQualityGraph

Matched: financial, language, markets, natural, processing

66match

Finding 21391 source

AI, especially natural language processing, is revolutionizing financial modeling by enhancingnot replacingclassic models like CAPM ($\text{CAPM}$), Markowitz Mean-Variance Optimization, and Black-Litterman ($\text{BLM}$), making them more accurate and responsive.

LexicalMeaningQualityGraph

Matched: financial, language, markets, natural, processing

66match

Finding 51401 source

The research contributes innovative methods by extracting key financial terms and incorporating market premiums, while highlighting trends like mean reversion after negative news, despite noted segmentation challenges for future improvement.

LexicalMeaningQualityGraph

Matched: financial, language, markets, natural, processing

65match

Finding 51381 source

The study reveals that integrating expert financial insights with 11-year market return data significantly enhances sentiment analysis, merging tailored finance-specific lexicons with advanced segmentation to improve investment decision-making in Japan.

LexicalMeaningQualityGraph

Matched: financial, language, markets, natural, processing

64match

Finding 51391 source

Surprisingly, a custom-built polarity dictionary using finance-specific keywords and refined segmentation techniques outperforms generic methods, delivering superior predictive accuracy for Japanese stock market trends and enhancing investment sentiment analysis remarkably.

LexicalMeaningQualityGraph

Matched: financial, language, markets, natural, processing

63match

Finding 60631 source

Artificial intelligence transforms finance by streamlining merger and acquisition processes, enhancing due diligence, while natural language processing harnesses data from Google Trends and YouTube to reshape stock analysis and forecasting.

LexicalMeaningQualityGraph

Matched: financial, language, markets, natural, processing

63match

Finding 37741 source

Authors introduce a synchronized dataset merging voice and text with deep learning, proposing VoiceAN and LanguageAN indicators, though audio noise and sentiment biases significantly constrain this innovative monetary policy analysis.

LexicalMeaningQualityGraph

Matched: financial, language, markets, natural, processing

63match

Finding 51411 source

Integrating market return data with sentiment analysis, this study constructs innovative polarity dictionaries that outperform ChatGPT for the Japanese stock market. Blending expert knowledge and textual analysis, the paper introduces a novel methodology $$\text{Innovative-Approach}$$, directly incorporating financial market dynamics, thus offering a compelling perspective for financial news and sentiment evaluation.

LexicalMeaningQualityGraph

Matched: financial, language, markets, natural, processing

62match

Finding 37731 source

Unexpectedly, positive vocal signals increase yields for Germany, France, and Spain, while negative cues markedly raise Italian yields, reflecting country-specific investor reactions that alter risk-free rates and market risk premiums.

LexicalMeaningQualityGraph

Matched: financial, language, markets, natural, processing

62match

Finding 21411 source

The approach combines traditional financial theory with deep neural networks and large language models, preserving interpretability for compliance but facing challenges like AI error control, data quality, and ethical concerns needing further research.

LexicalMeaningQualityGraph

Matched: financial, language, markets, natural, processing

62match

Finding 45611 source

The research highlights how sophisticated NLP tools can uncover predictive signals missed by older models, but notes practical challenges in real-world trading and the risk of overfitting remain unresolved.

LexicalMeaningQualityGraph

Matched: financial, language, markets, natural, processing

62match

Finding 37751 source

This paper innovatively applies Speech Emotion Recognition and NLP to assess central bank communications impact on bond yields, offering novel insights for fixed income and quantitative finance research. Its distinctive methodology integrates vocal and verbal cues with asset pricing, creating perspectives and avenues in computational financial and bond market analysis.

LexicalMeaningQualityGraph

Matched: financial, language, markets, natural, processing

61match

Finding 45591 source

A major study used advanced language models like ChatGPT, Claude, and Gemini to analyze sentiment in over 11,000 Japanese 10-K reports, covering 70 million words from 2014 to 2023.

LexicalMeaningQualityGraph

Matched: financial, language, markets, natural, processing

61match

Finding 30781 source

The approach achieves a remarkable 77--86% accuracyfar above the 43--66% of existing modelsdespite data scarcity, but its reliance on pre-trained models may limit generalizability across other central bank statements.

LexicalMeaningQualityGraph

Matched: financial, language, markets, natural, processing

61match

Finding 52661 source

The review of 84 studies introduces hybrid modeling and knowledge generation prompting, highlighting significant strengths and limitations while charting LLMs' disruptive potential and prompting future improvements across global financial ecosystems.

LexicalMeaningQualityGraph

Matched: financial, language, markets, natural, processing

61match

Finding 30771 source

Leveraging pre-trained BERT as a reward signal, the system highlights key FOMC minute sections, applies Open Information Extraction, and transforms complex text into structured data for highly accurate predictive modeling.

LexicalMeaningQualityGraph

Matched: financial, language, markets, natural, processing

61match

Finding 30761 source

A new consequence-guided extraction system by T. Cha and D. Lee uses advanced NLP and reinforcement learning to predict financial market reactions to FOMC communications, outperforming traditional methods significantly.

LexicalMeaningQualityGraph

Matched: financial, language, markets, natural, processing

61match

Finding 45601 source

Surprisingly, LLM-derived sentiment scores showed a significant negative correlation with future stock returnsmore negative sentiment predicted better performancechallenging the efficient market hypothesis and outperforming traditional dictionary-based methods.

LexicalMeaningQualityGraph

Matched: financial, language, markets, natural, processing

61match

Finding 30791 source

This paper uniquely combines consequence-guided information extraction and BERT-based reinforcement learning to predict central bank communication effects on markets, outperforming standard NLP in data-scarce settings. Its originality lies in integrating structured extraction with RL, offering novel, compelling insights for quantitative finance, financial AI, and macroeconomic forecasting, despite building on existing frameworks.

LexicalMeaningQualityGraph

Matched: financial, language, markets, natural, processing

61match

Finding 52641 source

Survey reveals LLMs rapidly reshape equity markets by blending structured and unstructured data, enhancing prediction accuracy and decision-making through innovative quantitative methods combined with prompting, fine-tuning, reinforcement learning, and systems.

LexicalMeaningQualityGraph

Matched: financial, language, markets, natural, processing

61match

Finding 50561 source

The research shows that instruction tuning LLMs can significantly enhance financial sentiment analysis. Potential applications include improved market prediction tools and financial news analysis. Future research could explore broader financial tasks and further refine instruction tuning methods.

LexicalMeaningQualityGraph

Matched: financial, language, natural, processing

61match

Finding 64761 source

The research highlights the potential of combining social media sentiment with traditional stock data for better stock price predictions. Future research could expand datasets, include more variables, and explore different model architectures. Applications include improved investment strategies and real-time financial market analysis tools.

LexicalMeaningQualityGraph

Matched: financial, language, natural, processing

60match

Finding 42511 source

FinLLM-B, a dedicated large language model, revolutionizes financial breakout trading detection by outperforming GPT-3.5 and GPT-4 nearly 50% in average accuracy and 57% in perfection rate with exceptional breakthrough performance.

LexicalMeaningQualityGraph

Matched: financial, language, markets, natural, processing

60match

Finding 45621 source

This paper uniquely applies advanced LLMs (ChatGPT, Claude, Gemini) to sentiment analysis of Japanese 10-K reports, an underexplored dataset. Its findingthat LLM-derived sentiment predicts future stock returns while traditional methods do notchallenges the efficient market hypothesis, offering novel insights and significant implications for both academic research and investment practice.

LexicalMeaningQualityGraph

Matched: financial, language, markets, natural, processing

60match

Finding 42521 source

Researchers introduce the first dedicated financial breakout dataset, employing a multi-stage framework that segments detection into S1, S2, and S3 tasks, enabling enhanced error reduction and detailed reasoning with precision.

LexicalMeaningQualityGraph

Matched: financial, language, markets, natural, processing

60match

Finding 21401 source

A standout finding is AI-driven sentiment analysis, which creates 'sentiment-aware' versions of CAPM and BLM, capturing investor mood and market anomalies for more personalized, robust investment strategies using alternative data sources.

LexicalMeaningQualityGraph

Matched: financial, language, markets, natural, processing

59match

Finding 42531 source

Using minute-level footprint data, the study combines manual annotation and a dual-model design separating detection from report generation, though static data reliance limits accuracy on complex subtasks for future improvement.

LexicalMeaningQualityGraph

Matched: financial, language, markets, natural, processing

59match

Finding 52281 source

The study observes open-source practices, challenges in code maintenance, limited non-English data and alternative method usage, and suggests replacing machine learning metrics with financial-specific measures like $$Sharpe\\ Ratio$$ for performance validation.

LexicalMeaningQualityGraph

Matched: financial, language, markets, natural, processing

59match

Finding 52651 source

Researchers integrate qualitative news insights by converting them into numerical signals, powering stock trend prediction through frameworks like Ploutos, StockTime, and benchmarks such as InvestorBench, despite scalability and interpretability challenges.

LexicalMeaningQualityGraph

Matched: financial, language, markets, natural, processing

59match

Finding 43941 source

The research highlights the potential of weak supervision and sentiment analysis in improving cryptocurrency forecasts. Future research could explore other financial markets and refine sentiment aggregation methods. Applications include better trading strategies and financial decision-making tools.

LexicalMeaningQualityGraph

Matched: financial, language, markets, natural, processing